Rapid diagnosis of Covid-19 infections by a progressively growing GAN and CNN optimisation

BACKGROUND AND OBJECTIVE

Covid-19 infections are spreading around the globe since December 2019. Several diagnostic methods were developed based on biological investigations and the success of each method depends on the accuracy of identifying Covid infections. However, access to diagnostic tools can be limited, depending on geographic region and the diagnosis duration plays an important role in treating Covid-19. Since the virus causes pneumonia, its presence can also be detected using medical imaging by Radiologists. Hospitals with X-ray capabilities are widely distributed all over the world, so a method for diagnosing Covid-19 from chest X-rays would present itself. Studies have shown promising results in automatically detecting Covid-19 from medical images using supervised Artificial neural network (ANN) algorithms. The major drawback of supervised learning algorithms is that they require huge amounts of data to train. Also, the radiology equipment is not computationally efficient for deep neural networks. Therefore, we aim to develop a Generative Adversarial Network (GAN) based image augmentation to optimize the performance of custom, light, Convolutional networks used for the classification of Chest X-rays (CXR).

METHODS

A Progressively Growing Generative Adversarial Network (PGGAN) is used to generate synthetic and augmented data to supplement the dataset. We propose two novel CNN architectures to perform the Multi-class classification of Covid-19, healthy and pneumonia affected Chest X-rays. Comparisons have been drawn to the state of the art models and transfer learning methods to evaluate the superiority of the networks. All the models are trained using enhanced and augmented X-ray images and are compared based on classification metrics.

RESULTS

The proposed models had extremely high classification metrics with proposed Architectures having test accuracy of 98.78% and 99.2% respectively while having 40% lesser training parameters than their state of the art counterpart.

CONCLUSION

In the present study, a method based on artificial intelligence is proposed, leading to a rapid diagnostic tool for Covid infections based on Generative Adversarial Network (GAN) and Convolutional Neural Networks (CNN). The benefit will be a high accuracy of detection with up to 99% hit rate, a rapid diagnosis, and an accessible Covid identification method by chest X-ray images.

Generative adversarial network based data augmentation for CNN based detection of Covid-19

Covid-19 has been a global concern since 2019, crippling the world economy and health. Biological diagnostic tools have since been developed to identify the virus from bodily fluids and since the virus causes pneumonia, which results in lung inflammation, the presence of the virus can also be detected using medical imaging by expert radiologists. The success of each diagnostic method is measured by the hit rate for identifying Covid infections. However, the access for people to each diagnosis tool can be limited, depending on the geographic region and, since Covid treatment denotes a race against time, the diagnosis duration plays an important role. Hospitals with X-ray opportunities are widely distributed all over the world, so a method investigating lung X-ray images for possible Covid-19 infections would offer itself. Promising results have been achieved in the literature in automatically detecting the virus using medical images like CT scans and X-rays using supervised artificial neural network algorithms. One of the major drawbacks of supervised learning models is that they require enormous amounts of data to train, and generalize on new data. In this study, we develop a Swish activated, Instance and Batch normalized Residual U-Net GAN with dense blocks and skip connections to create synthetic and augmented data for training. The proposed GAN architecture, due to the presence of instance normalization and swish activation, can deal with the randomness of luminosity, that arises due to different sources of X-ray images better than the classical architecture and generate realistic-looking synthetic data. Also, the radiology equipment is not generally computationally efficient. They cannot efficiently run state-of-the-art deep neural networks such as DenseNet and ResNet effectively. Hence, we propose a novel CNN architecture that is 40% lighter and more accurate than state-of-the-art CNN networks. Multi-class classification of the three classes of chest X-rays (CXR), ie Covid-19, healthy and Pneumonia, is performed using the proposed model which had an extremely high test accuracy of 99.2% which has not been achieved in any previous studies in the literature. Based on the mentioned criteria for developing Corona infection diagnosis, in the present study, an Artificial Intelligence based method is proposed, resulting in a rapid diagnostic tool for Covid infections based on generative adversarial and convolutional neural networks. The benefit will be a high accuracy of lung infection identification with 99% accuracy. This could lead to a support tool that helps in rapid diagnosis, and an accessible Covid identification method using CXR images.

Development of convolutional neural networks for recognition of tenogenic differentiation based on cellular morphology

BACKGROUND AND OBJECTIVE

The use of automated systems for image recognition is highly preferred for regenerative medicine applications to evaluate stem cell differentiation early in the culturing state with non-invasive methodologies instead of invasive counterparts. Bone marrow-derived mesenchymal stem cells (BMSCs) are able to differentiate into desired cell phenotypes, and thereby promise a proper cell source for tendon regeneration. The therapeutic success of stem cell therapy requires cellular characterization prior to the implantation of cells. The foremost problem is that traditional characterization techniques require cellular material which would be more useful for cell therapy, complex laboratory procedures, and human expertise. Convolutional neural networks (CNNs), a class of deep neural networks, have recently made great improvements in image-based classifications, recognition, and detection tasks. We, therefore, aim to develop a potential CNN model in order to recognize differentiated stem cells by learning features directly from image data of unlabelled cells.

METHODS

The differentiation of bone marrow mesenchymal stem cells (BMSCs) into tenocytes was induced with the treatment of bone morphogenetic protein-12 (BMP-12). Following the treatment and incubation step, the phase-contrast images of cells were obtained and immunofluorescence staining has been applied to characterize the differentiated state of BMSCs. CNN models were developed and trained with the phase-contrast cell images. The comparison of CNN models was performed with respect to prediction performance and training time. Moreover, we have evaluated the effect of image enhancement method, data augmentation, and fine-tuning training strategy to increase classification accuracy of CNN models. The best model was integrated into a mobile application.

RESULTS

All the CNN models can fit the biological data extracted from immunofluorescence characterization. CNN models enable the cell classification with satisfactory accuracies. The best result in terms of accuracy and training time is achieved by the model proposed based on Inception-ResNet V2 trained from scratch using image enhancement and data augmentation strategies (96.80%, 434.55 sec).

CONCLUSION

Our study reveals that the CNN models show good performance by identifying stem cell differentiation. Importantly this technique provides a faster and real-time tool in comparison to traditional methods enabling the adjustment of culture conditions during cultivation to improve the yield of therapeutic stem cells.